-
MAVLab, TU Delft
- NTG->NKG->YYZ->ZRH->AMS
- @DavidYilun
Highlights
- Pro
Stars
A Smooth Representation of SO(3) for Deep Rotation Learning with Uncertainty.
Learning with 3D rotations, a hitchhiker’s guide to SO(3) - ICML 2024
Depth Pro: Sharp Monocular Metric Depth in Less Than a Second.
The official implementation of "Motion-prior Contrast Maximization for Dense Continuous-Time Motion Estimation" (ECCV 2024)
Official PyTorch implementation for "Efficient Meshflow and Optical Flow Estimation from Event Cameras"
Structured state space sequence models
[CVPR'24 Spotlight] The official implementation of "State Space Models for Event Cameras"
[CVPR 2022] Deep Equilibrium Optical Flow Estimation
Code for the paper "Low Latency Automotive Vision with Event Cameras", published in Nature
End-to-end optimal quadcopter control through Supervised Learning
🤖 Machine Learning Summer School deadlines
PyTorch code and models for V-JEPA self-supervised learning from video.
Samples which demonstrate features provided by cuSNN
Masked Event Modeling: Self-Supervised Pretraining for Event Cameras (WACV '24)
A procedural Blender pipeline for photorealistic training image generation
dkms module of Linux i915 driver with SR-IOV support
A repository collating interesting and/or influential predictive coding papers
Code for the paper "Predictive Coding Approximates Backprop along Arbitrary Computation Graphs"
PyTorch-based code for training fully-connected and convolutional networks using backpropagation (BP), feedback alignment (FA), direct feedback alignment (DFA), and direct random target projection …